{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:39:26Z","timestamp":1740123566518,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,4,30]],"date-time":"2021-04-30T00:00:00Z","timestamp":1619740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,30]],"date-time":"2021-04-30T00:00:00Z","timestamp":1619740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Electron Test"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1007\/s10836-021-05945-1","type":"journal-article","created":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T08:24:38Z","timestamp":1620030278000},"page":"409-422","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fault Tolerant Lanczos Eigensolver via an Invariant Checking Method"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9288-6766","authenticated-orcid":false,"given":"Felix","family":"Loh","sequence":"first","affiliation":[]},{"given":"Kewal K.","family":"Saluja","sequence":"additional","affiliation":[]},{"given":"Parameswaran","family":"Ramanathan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,4,30]]},"reference":[{"key":"5945_CR1","doi-asserted-by":"crossref","unstructured":"Agerwala T (2010) Exascale computing: The challenges and opportunities in the next decade. In Proc. of the International Symposium on High Performance Computer Architecture (HPCA)","DOI":"10.1109\/HPCA.2010.5416662"},{"key":"5945_CR2","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1090\/qam\/42792","volume":"9","author":"W Arnoldi","year":"1951","unstructured":"Arnoldi W (1951) The principle of minimized iterations in the solution of the matrix eigenvalue problem. Quart Appl Math 9:17\u201329","journal-title":"Quart Appl Math"},{"key":"5945_CR3","doi-asserted-by":"crossref","unstructured":"Balay S, Abhyankar S, Adams M, Brown J, Brune P, Buschelman K, Dalcin L, Eijkhout V, Gropp W, Kaushik D, Knepley M, May D, McInnes L, Rupp K, Sanan P, Smith B, Zampini S, Zhang H, Zhang H (2017) PETSc users manual. Technical Report ANL-95\/11 - Revision 3.8, Argonne National Laboratory","DOI":"10.2172\/1409218"},{"key":"5945_CR4","doi-asserted-by":"crossref","unstructured":"Balay S, Gropp W, McInnes L, Smith B (1997) Efficient management of parallelism in object oriented numerical software libraries. In E.\u00a0Arge, A.\u00a0M. Bruaset, and H.\u00a0P. Langtangen, editors, Modern Software Tools in Scientific Computing, pages 163\u2013202. Birkh\u00e4user Press","DOI":"10.1007\/978-1-4612-1986-6_8"},{"key":"5945_CR5","doi-asserted-by":"crossref","unstructured":"Braun C, Halder S, Wunderlich HJ (2014) A-ABFT: Autonomous algorithm-based fault tolerance for matrix multiplications on graphics processing units. In Proc. of the IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN), pages 443\u2013454","DOI":"10.1109\/DSN.2014.48"},{"key":"5945_CR6","doi-asserted-by":"crossref","unstructured":"Bronevetsky G, de\u00a0Supinski B (2008) Soft error vulnerability of iterative linear algebra methods. In Proc. of the International Conference on Supercomputing, pages 155\u2013164","DOI":"10.1145\/1375527.1375552"},{"key":"5945_CR7","doi-asserted-by":"crossref","unstructured":"Chen Z (2013) Online-ABFT: An online algorithm based fault tolerance scheme for soft error detection in iterative methods. In Proc. of the Symposium on Principles and Practice of Parallel Programming (PPoPP), pages 167\u2013176","DOI":"10.1145\/2517327.2442533"},{"key":"5945_CR8","doi-asserted-by":"crossref","unstructured":"Chen J, Liang X, Chen Z (2016) Online algorithm-based fault tolerance for Cholesky decomposition on heterogeneous systems with GPUs. In Proc. of the IEEE International Parallel and Distributed Processing Symposium (IPDPS)","DOI":"10.1109\/IPDPS.2016.81"},{"key":"5945_CR9","doi-asserted-by":"crossref","unstructured":"Davis TA, Hu Y (2011) The University of Florida sparse matrix collection. ACM Trans Math Soft\u00a038(1):1:1\u20131:25","DOI":"10.1145\/2049662.2049663"},{"key":"5945_CR10","doi-asserted-by":"crossref","unstructured":"Elliott J, Hoemmen M, Mueller F (2014) Evaluating the impact of SDC on the GMRES iterative solver. In Proc. of the IEEE International Parallel and Distributed Processing Symposium (IPDPS)\u00a0pages 1193\u20131202","DOI":"10.1109\/IPDPS.2014.123"},{"key":"5945_CR11","volume-title":"Matrix Computations","author":"GH Golub","year":"1996","unstructured":"Golub GH, van Loan CF (1996) Matrix Computations, 3rd edn. Johns Hopkins University Press, Baltimore, MD","edition":"3"},{"issue":"5","key":"5945_CR12","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1109\/TPDS.2014.2320502","volume":"26","author":"D Hakkarinen","year":"2015","unstructured":"Hakkarinen D, Wu P, Chen Z (2015) Fail-stop failure algorithm-based fault tolerance for Cholesky decomposition. IEEE Trans Par Distr Sys 26(5):1323\u20131335","journal-title":"IEEE Trans Par Distr Sys"},{"key":"5945_CR13","unstructured":"Hernandez V, Roman JE, Tomas A, Vidal V (2006) Lanczos methods in SLEPc. Technical Report STR-5, Universitat Polit\u00e8cnica de Val\u00e8ncia. Available at http:\/\/slepc.upv.es"},{"issue":"3","key":"5945_CR14","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1145\/1089014.1089019","volume":"31","author":"V Hernandez","year":"2005","unstructured":"Hernandez V, Roman JE, Vidal V (2005) SLEPc: A scalable and flexible toolkit for the solution of eigenvalue problems. ACM Trans Math Soft 31(3):351\u2013362","journal-title":"ACM Trans Math Soft"},{"issue":"4","key":"5945_CR15","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1177\/1094342009347711","volume":"23","author":"MA Heroux","year":"2009","unstructured":"Heroux MA (2009) Software challenges for extreme scale computing: Going from petascale to exascale systems. Int J High Perf Comput Appl 23(4):437\u2013439","journal-title":"Int J High Perf Comput Appl"},{"key":"5945_CR16","doi-asserted-by":"crossref","unstructured":"Huang KH, Abraham JA (1984) Algorithm-based fault tolerance for matrix operations. IEEE Trans Comp\u00a0C-33(6):518\u2013528","DOI":"10.1109\/TC.1984.1676475"},{"key":"5945_CR17","doi-asserted-by":"crossref","unstructured":"Kim H, Vuduc R, Baghsorkhi S, Choi J, Hwu W (2012) Performance analysis and tuning for general purpose graphics processing units (GPGPU). Synthesis Lectures on Computer Architecture","DOI":"10.2200\/S00451ED1V01Y201209CAC020"},{"issue":"2","key":"5945_CR18","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1137\/S1064827500366124","volume":"23","author":"A Knyazev","year":"2001","unstructured":"Knyazev A (2001) Toward the optimal preconditioned eigensolver: Locally optimal block preconditioned conjugate gradient method. SIAM J Sci Comput 23(2):517\u2013541","journal-title":"SIAM J Sci Comput"},{"issue":"4","key":"5945_CR19","doi-asserted-by":"publisher","first-page":"255","DOI":"10.6028\/jres.045.026","volume":"45","author":"C Lanczos","year":"1950","unstructured":"Lanczos C (1950) An iteration method for the solution of the eigenvalue problem of linear differential and integral operators. J Res Nat Bur Stand 45(4):255\u2013282","journal-title":"J Res Nat Bur Stand"},{"key":"5945_CR20","doi-asserted-by":"crossref","unstructured":"Loh F, Ramanathan P, Saluja KK (2015) Transient fault resilient QR factorization on GPUs. In Proc. of the 5th Workshop on Fault Tolerance for HPC at eXtreme Scale, FTXS \u201915, pages 63\u201370","DOI":"10.1145\/2751504.2751505"},{"key":"5945_CR21","doi-asserted-by":"crossref","unstructured":"Loh F, Saluja KK, Ramanathan P (2016) Fault tolerance through invariant checking for iterative solvers. In Proc. of the International Conference on VLSI Design and International Conference on Embedded Systems (VLSID), pages 481\u2013486","DOI":"10.1109\/VLSID.2016.25"},{"key":"5945_CR22","doi-asserted-by":"crossref","unstructured":"Loh F, Saluja KK, Ramanathan P (2020) Fault tolerance through invariant checking for the lanczos eigensolver. In Proc. of the International Conference on VLSI Design and International Conference on Embedded Systems (VLSID), pages 13\u201318","DOI":"10.1109\/VLSID49098.2020.00020"},{"key":"5945_CR23","doi-asserted-by":"crossref","unstructured":"Nie B, Tiwari D, Gupta S, Smirni E, Rogers JH (2016) A large-scale study of soft-errors on GPUs in the field. In Proc. of the International Symposium on High Performance Computer Architecture (HPCA), pages 519\u2013530","DOI":"10.1109\/HPCA.2016.7446091"},{"key":"5945_CR24","unstructured":"NVIDIA (2016) NVIDIA GeForce GTX 1080. White Paper"},{"key":"5945_CR25","doi-asserted-by":"crossref","unstructured":"Oboril F, Tahoori MB, Heuveline V, Lukarski D, Weiss JP (2011) Numerical defect correction as an algorithm-based fault tolerance technique for iterative solvers. In Proc. of the IEEE Pacific Rim International Symposium on Dependable Computing (PRDC), pages 144\u2013153","DOI":"10.1109\/PRDC.2011.26"},{"key":"5945_CR26","unstructured":"Shivakumar P, Kistler M, Keckler SW, Burger D, Alvisi L (2003) Modeling the impact of device and pipeline scaling on the soft error rate of processor elements. Technical Report 2002-19, Dept. of Computer Sciences, The University of Texas at Austin"},{"key":"5945_CR27","doi-asserted-by":"crossref","unstructured":"Scholl A, Braun C, Kochte MA, Wunderlich H (2015) Low-overhead fault-tolerance for the preconditioned conjugate gradient solver. In Proc. of the IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFTS), pages 60\u201365","DOI":"10.1109\/DFT.2015.7315136"},{"key":"5945_CR28","doi-asserted-by":"crossref","unstructured":"Shantharam M, Srinivasmurthy S, Raghavan P (2012) Fault tolerant preconditioned conjugate gradient for sparse linear system solution. In Proc. of the International Conference on Supercomputing, pages 69\u201378","DOI":"10.1145\/2304576.2304588"},{"issue":"6","key":"5945_CR29","doi-asserted-by":"publisher","first-page":"2570","DOI":"10.1109\/TNS.2015.2495130","volume":"62","author":"N Siefert","year":"2015","unstructured":"Siefert N, Jahinuzzaman S, Velamala J, Ascazubi R, Patel N, Gill B, Basile J, Hicks J (2015) Soft error rate improvements in 14-nm technology featuring second-generation 3D tri-gate transistors. IEEE Trans Nucl Sci 62(6):2570\u20132577","journal-title":"IEEE Trans Nucl Sci"},{"key":"5945_CR30","doi-asserted-by":"crossref","unstructured":"Sloan J, Kumar R, Bronevetsky G (2012) Algorithmic approaches to low overhead fault detection for sparse linear algebra. In Proc. of the IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN), pages 1\u201312","DOI":"10.1109\/DSN.2012.6263938"},{"key":"5945_CR31","doi-asserted-by":"crossref","unstructured":"Wu P, Guan Q, DeBardeleben N, Blanchard S, Tao D, Liang X, Chen J, Chen Z (2016) Towards practical algorithm based fault tolerance in dense linear algebra. In Proc. of the 25th International Symposium on High-performance Parallel and Distributed Computing, HPDC \u201916, pages 31\u201342","DOI":"10.1145\/2907294.2907315"}],"container-title":["Journal of Electronic Testing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10836-021-05945-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10836-021-05945-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10836-021-05945-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,31]],"date-time":"2021-08-31T00:02:53Z","timestamp":1630368173000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10836-021-05945-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,30]]},"references-count":31,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["5945"],"URL":"https:\/\/doi.org\/10.1007\/s10836-021-05945-1","relation":{},"ISSN":["0923-8174","1573-0727"],"issn-type":[{"type":"print","value":"0923-8174"},{"type":"electronic","value":"1573-0727"}],"subject":[],"published":{"date-parts":[[2021,4,30]]},"assertion":[{"value":"3 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}